DATA CLASSIFIER SYSTEM, DATA CLASSIFIER METHOD AND DATA CLASSIFIER PROGRAM

• US 20110179037A1
• Filed: 07/29/2009
• Published: 07/21/2011
• Est. Priority Date: 07/30/2008
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Mizuguchi, Hironori, Kusui, Dai, Tateishi, Kenji, Hosomi, Itaru
• Granted Patent: US 9,361,367 B2
• Time in Patent Office: Days
• US Class Current: 707/740
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/353 into predefined classes

Abstract

A data classifier system of the present invention selects a plurality of classifications correlated to data groups so as to output classification axes based on hierarchical classifications and data groups. The data classifier system includes a basic category accumulation means, a classification axis candidate creation means and a priority calculation means. The basic category accumulation means accumulates classifications serving as basic categories used for selecting desired classifications in advance. The classification axis candidate creation means creates classification axis candidates based on combinations of classifications each correlated to at least one data among descendant classifications of each basic category. The priority calculation means calculates priorities with respect to the classification axis candidates created by the classification axis candidate creation means based on hierarchical distances of classifications in the classified hierarchy.

Claims

1. A data classifier system which selects a plurality of classifications correlated to data groups based on hierarchical classifications and data groups so as to output classification axes, said data classifier system comprising:

a basic category accumulation means which accumulates classifications serving as basic categories used for selecting desired classifications in advance;

a classification axis candidate creation means which creates classification axis candidates based on combinations of classifications each correlated to at least one data among descendant classifications of each basic category; and

a priority calculation means which calculates priorities with respect to the classification axis candidates created by the classification axis candidate creation means based on hierarchical distances of classifications in a classified hierarchy.

2. The data classifier system according to claim 1, wherein the priority calculation means changes priorities in response to lengths of classifications leading to a common ancestor in the classified hierarchy as the hierarchical distances of classifications.

3. The data classifier system according to claim 1, wherein the priority calculation means calculates hierarchical distances of classifications in the classified hierarchy and determines the priorities of the classification axis candidates based on at least one of depths of classifications in the classified hierarchy, data quantities of classifications and data redundancies of classifications.

4. The data classifier system according to claim 1, wherein the classification axis candidate creation means reduces the number of classification axis candidates based on data quantities of classifications and hierarchical distances of classifications in the classified hierarchy.

5. The data classifier system according to claim 1, wherein the classification axis candidate creation means selects classification axes satisfying a condition that data quantities of classifications are larger than a predetermined value or fall within an upper range in a descending order of data quantities and a condition that lengths of classifications leading to a common ancestor fall within a specific range.

6. The data classifier system according to claim 1 further comprising a display control means which inputs the classification axis candidates created by the classification axis candidate creation means and the priorities calculated by the priority calculation means so as to perform display control on them in connection with data groups, wherein the display control means is configured to display the classification axis candidates in an order of the priorities, select the classification axis candidates so as to change over and display classification axes, and select classifications in the classification axes so as to select or limit data groups.

7. The data classifier system according to claim 1 further comprising a data retrieval means which retrieves data groups based on retrieval keywords so as to output the retrieval result of data groups to the classification axis candidate creation means,

wherein the classification axis candidate creation means creates classification axis candidates based on the retrieval result of the data retrieval means, and

wherein the priority calculation means calculates priorities of classification axes correlated to the data groups retrieved by the data retrieval means.

8. The data classifier system according to claim 1 further comprising a data correlation means which inputs hierarchical classifications and data groups so as to correlate the input classifications and the input data groups.

9. A data classifier system which selects a plurality of classifications correlated to data groups so as to create classification axes based on hierarchical classifications and data groups and thereby output combinations of classification axes, said data classifier system comprising:

a basic category accumulation means which accumulates classifications serving as basic categories used for selecting desired classifications in advance;

a multidimensional classification axis candidate creation means which creates classification axis candidates based on combinations of classifications each correlated to at least one data among descendant classifications of each basic category and which creates multidimensional classification axis candidates each combining a plurality of classification axis candidates; and

a multidimensional priority calculation means which calculates priorities with respect to the multidimensional classification axis candidates created by the multidimensional classification axis candidate creation means based on hierarchical distances of classifications in a classified hierarchy.

10. The data classifier system according to claim 9, wherein the multidimensional priority calculation means changes priorities of the multidimensional classification axis candidates in response to lengths of classifications leading to a common ancestor in the classified hierarchy as the hierarchical distances of classifications.

11. The data classifier system according to claim 9, wherein the multidimensional priority calculation means calculates hierarchical distances of classifications in the classified hierarchy and determines the priorities of the multidimensional classification axis candidates based on at least one of depths of classifications in the classified hierarchy, data quantities of classifications and data redundancies of classifications.

12. The data classifier system according to claim 9, wherein the multidimensional classification axis candidate creation means reduces the number of multidimensional classification axis candidates based on data quantities of classifications of classification axes of each dimension and hierarchical distances of classifications of classification axes of each dimension.

13. The data classifier system according to claim 9, wherein the multidimensional classification axis candidate creation means selects multidimensional classification axes including classifications in which data quantities of classifications of classification axes of each dimension are larger than a predetermined value or fall within an upper range in a descending order of data quantities and classifications in which hierarchical distances of classifications of classification axes of each dimension, i.e. lengths of classifications leading to a common ancestor, fall within a specific range.

14. The data classifier system according to claim 9 further comprising a multidimensional display means which inputs the multidimensional classification axis candidates created by the multidimensional classification axis candidate creation means and the priorities calculated by the multidimensional priority calculation means so as to perform display control on them in connection with data groups in a list form or in a table form,

wherein the multidimensional display control means selects the multidimensional classification axis candidates so as to display and allocate classifications of each dimension to the list form or the table form, and subsequently selects one or plural classifications so as to display at least one of data quantities, data names, data attributes and characteristic terms with respect to the selected classifications.

15. The data classifier system according to claim 9 further comprising a data retrieval means which retrieves data groups based on retrieval keywords so as to output the retrieval result of data groups to the multidimensional classification axis candidate creation means.

16. The data classifier system according to claim 9 further comprising a data correlation means which inputs hierarchical classifications and data groups so as to correlate the input classifications and the input data groups.

17. A data classifier method which selects a plurality of classifications correlated to data groups based on hierarchical classifications and data groups so as to output classification axes, said data classifier method comprising:

a classification axis candidate creation process which accumulates classifications serving as basic categories used for selecting desired classifications in a database in advance and which creates classification axis candidates based on combinations of classifications each correlated to at least one data among descendant classifications of each basic category; and

a priority calculation process which calculates priorities with respect to the classification axis candidates created by the classification axis candidate creation process based on hierarchical distances of classifications in a classified hierarchy.

18. The data classifier method according to claim 17, wherein the priority calculation process changes priorities in response to lengths of classifications leading to a common ancestor in the classified hierarchy as the hierarchical distances of classifications.

19. The data classifier method according to claim 17, wherein the priority calculation process calculates hierarchical distances of classifications in the classified hierarchy and determines the priorities of the classification axis candidates based on at least one of depths of classifications in the classified hierarchy, data quantities of classifications and data redundancies of classifications.

20. A data classifier method which selects a plurality of classifications correlated to data groups so as to create classification axes based on hierarchical classifications and data groups and thereby output combinations of classification axes, said data classifier method comprising:

a multidimensional classification axis candidate creation process which accumulates classifications serving as basic categories used for selecting desired classifications in a database in advance, which creates classification axis candidates based on combinations of classifications each correlated to at least one data among descendant classifications of each basic category, and which creates multidimensional classification axis candidates each combining a plurality of classification axis candidates; and

a multidimensional priority calculation process which calculates priorities with respect to the multidimensional classification axis candidates created by the multidimensional classification axis candidate creation means based on hierarchical distances of classifications in a classified hierarchy.

21. The data classifier method according to claim 20, wherein the multidimensional priority calculation process changes priorities of the multidimensional classification axis candidates in response to lengths of classifications leading to a common ancestor in the classified hierarchy as the hierarchical distances of classifications.

22. The data classifier method according to claim 20, wherein the multidimensional priority calculation process calculates hierarchical distances of classifications in the classified hierarchy and determines the priorities of the multidimensional classification axis candidates based on at least one of depths of classifications in the classified hierarchy, data quantities of classifications and data redundancies of classifications.

23. A data classifier program which selects a plurality of classifications correlated to data groups based on hierarchical classifications and data groups so as to output classification axes, said data classifier program causing a computer equipped with a basic category accumulation means, which accumulates classifications serving as basic categories used for selecting desired classifications in advance, to perform

a classification axis candidate creation process which creates classification axis candidates based on combinations of classifications each correlated to at least one data among descendant classifications of each basic category;

and

a priority calculation process which calculates priorities with respect to the classification axis candidates created by the classification axis candidate creation process based on hierarchical distances of classifications in a classified hierarchy.

24. The data classifier program according to claim 23 causing the computer to have the priority calculation process change priorities in response to lengths of classifications leading to a common ancestor in the classified hierarchy as the hierarchical distances of classifications.

25. A data classifier program which selects a plurality of classifications correlated to data groups so as to create classification axes based on hierarchical classifications and data groups and thereby output combinations of classification axes, said data classifier program causes a computer equipped with a basic category accumulation means, which accumulates classifications serving as basic categories used for selecting desired classifications in advance, to perform

a multidimensional classification axis candidate creation process which creates classification axis candidates based on combinations of classifications each correlated to at least one data among descendant classifications of each basic category and which thereby creates multidimensional classification axis candidates each combining a plurality of classification axis candidates;

and

a multidimensional priority calculation process which calculates priorities with respect to the multidimensional classification axis candidates created by the multidimensional classification axis candidate creation process based on hierarchical distances of classifications in a classified hierarchy.

26. The data classifier program according to claim 25 causing the computer to have the multidimensional priority calculation process change priorities of the multidimensional classification axis candidates in response to lengths of classifications leading to a common ancestor in the classified hierarchy as the hierarchical distances of classifications.